The official Infisical MCP server (@infisical/mcp) that lets AI assistants work with Infisical's secrets-management API through function calling — reading, creating, updating, and deleting secrets, and managing projects, environments, folders, and project members — authenticating with a Machine Identity (universal auth) or an access token against Infisical Cloud or a self-hosted instance.
The server can read, create, update, and delete secrets (`get-secret`, `list-secrets`, `create-secret`, `update-secret`, `delete-secret`) in the projects and environments its identity can access, so deletions and edits affect real secrets., It can also create projects, environments, and folders and invite members to a project (`create-project`, `create-environment`, `create-folder`, `invite-members-to-project`), which change structure and access., Access is bounded by the Machine Identity or access token, not by tool naming; scope that identity to the minimum projects, environments, and permissions needed., Because this manages secrets, prefer a least-privilege identity and a non-production project when an agent acts autonomously., The universal-auth client secret or `INFISICAL_TOKEN` grants access to your secrets and must itself be treated as a secret.
Privacy notes
The `get-secret` and `list-secrets` tools return secret values to the LLM/MCP client, so plaintext secrets can be exposed to the model and its provider — a significant consideration for a secrets manager., Avoid pointing the server at production secrets; use a scoped, non-sensitive project for agent workflows where possible., The identity credentials (client ID/secret or access token) live in your MCP client config env block — keep that config out of version control and restrict access to it., When self-hosting, `INFISICAL_HOST_URL` targets your own instance, and requests plus credentials are sent there.
Author
Infisical
Submitted by
davion-knight
Claim status
unclaimed
Last verified
2026-07-08
Decision playbook
Review trust signals before you adopt
Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.
Compare context
Selected
0
Current score
78
Baseline
—
Delta
No baseline selected
No major trust-signal divergence detected in the current selection.
Source and provenance checks
Complete
Confirm ownership and provenance before trusting install instructions.
Source link availableRequired
Open the canonical repository and verify ownership.
Done
Source provenance statusRequired
Marked as source-backed.
Done
Metadata reviewed
Registry metadata indicates a reviewed listing.
Done
Safety and privacy checks
Complete
Validate risk disclosures before installation or API wiring.
Safety notes presentRequired
Review the listed safety guidance before running commands.
Done
Privacy notes presentRequired
Review data handling notes before connecting accounts or secrets.
Done
Trust level risk gateRequired
Trust level does not block evaluation.
Done
Package and install checks
Needs review
Check package metadata and artifact integrity signals.
Install payload available
Install or copy payload is available for review.
Done
Package verification flag
No package verification flag provided.
Pending
Checksum metadata
No checksum provided for downloaded artifact.
Pending
Compare-driven decision checks
Needs review
Use compare context to validate trade-offs before adoption.
Compare tray has multiple entries
Add at least one more entry to compare trust differences.
Pending
Baseline comparison available
No baseline peer selected yet.
Pending
Diverging trust signals identified
No major trust-signal divergence found.
Pending
Adoption plan
Balanced adoption plan
Current risk score 16/100. Use staged verification before broader rollout.
Risk 16
Pre-adoption checks
Validate source and review signals before any execution.
Confirm source provenanceRequired
Source URL/provenance metadata is present.
Done
Confirm metadata review state
Listing has review metadata.
Done
Verify install payload
Install/config payload exists and can be inspected.
Done
Security checks
Confirm safety, privacy, and package integrity signals.
Review safety notesRequired
Safety notes are present.
Done
Review privacy notesRequired
Privacy notes are present.
Done
Verify package integrity metadata
No package verification/checksum metadata.
Pending
Rollout
Adopt in controlled steps based on the selected plan.
Run in isolated sandbox firstRequired
Use a constrained sandbox and observe behavior across multiple tasks.
Pending
Roll out graduallyRequired
Roll out to a small cohort before wider usage.
Pending
Set monitoring and fallback
Define rollback path and monitor errors after adoption.
Pending
Evidence readiness
Evidence readiness matrix · balanced
Required evidence gates are covered (5/6 signals complete).
Risk 15
Source provenance
Present
Source repository/provenance is listed.
Required in this preset
Metadata review
Present
Review metadata is present.
Required in this preset
Safety notes
Present
Safety notes are present.
Required in this preset
Privacy notes
Present
Privacy notes are present.
Optional in this preset
Package integrity
Missing
Package integrity metadata is missing.
Optional in this preset
Install payload
Present
Install payload is available.
Required in this preset
Required evidence gates are covered for this preset.
Decision timeline
Decision timeline · balanced
5/6 steps complete with no blocking gaps for this preset.
Risk 14
triage
Confirm source provenanceRequired
Source/provenance metadata is available.
Done
triage
Check metadata review statusRequired
Review metadata is available.
Done
verify
Review safety notesRequired
Safety notes are available.
Done
verify
Review privacy notes
Privacy notes are available.
Done
verify
Validate package integrity metadata
Package integrity metadata is missing.
Pending
rollout
Verify install payload and commandsRequired
Install payload is available.
Done
No required blockers for this timeline preset.
Safety notes
The server can read, create, update, and delete secrets (`get-secret`, `list-secrets`, `create-secret`, `update-secret`, `delete-secret`) in the projects and environments its identity can access, so deletions and edits affect real secrets.
It can also create projects, environments, and folders and invite members to a project (`create-project`, `create-environment`, `create-folder`, `invite-members-to-project`), which change structure and access.
Access is bounded by the Machine Identity or access token, not by tool naming; scope that identity to the minimum projects, environments, and permissions needed.
Because this manages secrets, prefer a least-privilege identity and a non-production project when an agent acts autonomously.
The universal-auth client secret or `INFISICAL_TOKEN` grants access to your secrets and must itself be treated as a secret.
Privacy notes
The `get-secret` and `list-secrets` tools return secret values to the LLM/MCP client, so plaintext secrets can be exposed to the model and its provider — a significant consideration for a secrets manager.
Avoid pointing the server at production secrets; use a scoped, non-sensitive project for agent workflows where possible.
The identity credentials (client ID/secret or access token) live in your MCP client config env block — keep that config out of version control and restrict access to it.
When self-hosting, `INFISICAL_HOST_URL` targets your own instance, and requests plus credentials are sent there.
Prerequisites
Node.js and npm (the server runs via `npx -y @infisical/mcp`)
An Infisical account on Infisical Cloud or a self-hosted instance
Credentials — a Machine Identity universal-auth client ID and secret, or an access token (`INFISICAL_TOKEN`)
Optionally `INFISICAL_HOST_URL` for a self-hosted or dedicated instance (defaults to `https://app.infisical.com`)
An MCP-compatible client (Claude Desktop, Cursor, VS Code, etc.)
The Infisical MCP Server is the official Model Context Protocol server maintained by
Infisical. It lets LLMs and agentic clients work with
Infisical's secrets-management API through function calling — reading,
creating, updating, and deleting secrets, and managing projects, environments, folders,
and project members — on Infisical Cloud or a self-hosted instance.
It ships as the npm package @infisical/mcp
(v0.0.23, Apache-2.0), runs over stdio via npx, and authenticates with a Machine Identity
(universal auth, the default) or an access token. The optional INFISICAL_HOST_URL defaults to
https://app.infisical.com and can point at a self-hosted instance. Setup details live in the
repository README.
Source Review
The following real repository and package sources were fetched and reviewed for this entry:
README.md — the npx install command, the universal-auth and access-token auth methods and their environment variables, the INFISICAL_HOST_URL option, the client config blocks, and the tool list.
npm: @infisical/mcp — package name and version (0.0.23) and Apache-2.0 license.
Repository facts confirmed at review time: official Infisical organization, repository
Infisical/infisical-mcp-server, default branch main, not archived, and released as
@infisical/mcp v0.0.23 on npm.
Features
Secret operations — get-secret, list-secrets, create-secret, update-secret, and delete-secret read and manage secrets.
Projects — create-project and list-projects create and enumerate Infisical projects.
Environments & folders — create-environment and create-folder organize secrets within a project.
Membership — invite-members-to-project invites one or more members to a project.
Flexible auth — Machine Identity universal auth (client ID/secret, the default) or an access token (INFISICAL_TOKEN).
Cloud or self-hosted — targets Infisical Cloud by default, or a self-hosted/dedicated instance via INFISICAL_HOST_URL.
One-command install — runs via npx -y @infisical/mcp with no clone or build step.
Installation
Run the published package with npx. Universal auth (Machine Identity) is the default method:
INFISICAL_AUTH_METHOD accepts universal-auth (default) or access-token. INFISICAL_HOST_URL
defaults to https://app.infisical.com and can point at a self-hosted or dedicated Infisical
instance.
Use Cases
Conversational secret management — read, create, update, and delete secrets across environments from an agentic workflow.
Project bootstrapping — create projects, environments, and folders to structure a new codebase's configuration.
Onboarding — invite members to a project during setup.
Configuration review — list projects and secrets to audit what exists (with appropriate least-privilege access).
Self-hosted workflows — operate against a self-hosted Infisical instance via INFISICAL_HOST_URL.
Safety and Privacy
Reads and writes real secrets.get/list/create/update/delete-secret can expose and modify secret values; it can also create projects/environments/folders and invite members.
Secrets flow to the model.get-secret and list-secrets return secret values to the LLM/MCP client, so plaintext secrets can reach the model and its provider — the key consideration for a secrets manager.
Scope the identity. Access is bounded by the Machine Identity or token; grant only the projects, environments, and permissions needed, and prefer a non-production project for autonomous agents.
Credentials are secrets too. The universal-auth client secret or INFISICAL_TOKEN grants access to your vault — keep client config out of version control and restrict access.
Self-hosting.INFISICAL_HOST_URL sends requests and credentials to your own instance; confirm it is the intended target.
Duplicate Check
No existing entry in the directory matches this server. A search of all directory entries for
"infisical" across slugs, titles, repository URLs, and install commands returned no results, and there
is no prior entry pointing at github.com/Infisical/infisical-mcp-server or the npm package
@infisical/mcp. This is therefore a net-new, non-duplicate entry.
Show that Infisical MCP Server is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.
[](https://heyclau.de/entry/mcp/infisical-mcp-server)
How it compares
Infisical MCP Server side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
1 trust signal differ across this comparison (Submitter).
The official Infisical MCP server (@infisical/mcp) that lets AI assistants work with Infisical's secrets-management API through function calling — reading, creating, updating, and deleting secrets, and managing projects, environments, folders, and project members — authenticating with a Machine Identity (universal auth) or an access token against Infisical Cloud or a self-hosted instance.
The official Codacy MCP server (@codacy/codacy-mcp) that gives AI assistants access to the Codacy API for code quality, security, and coverage — listing repository and pull-request issues, retrieving file coverage and duplication, searching security (SRM) findings, inspecting analysis tools and patterns, and running local analysis with the Codacy CLI.
The official Render MCP server lets LLMs manage Render resources: create and manage web services, static sites, cron jobs, Postgres and Key-Value instances, monitor deploys, query logs and metrics, and run read-only SQL against Render Postgres.
The official Mux MCP server (@mux/mcp) that gives AI agents access to the Mux API for video and analytics. It uses a "Code Mode" scheme — exposing a documentation-search tool and a code tool that runs agent-written TypeScript against the Mux SDK in an isolated sandbox — to work with Mux Video (assets, live streams, playback IDs, uploads) and Mux Data (viewer metrics and monitoring).
✓The server can read, create, update, and delete secrets (`get-secret`, `list-secrets`, `create-secret`, `update-secret`, `delete-secret`) in the projects and environments its identity can access, so deletions and edits affect real secrets.
It can also create projects, environments, and folders and invite members to a project (`create-project`, `create-environment`, `create-folder`, `invite-members-to-project`), which change structure and access.
Access is bounded by the Machine Identity or access token, not by tool naming; scope that identity to the minimum projects, environments, and permissions needed.
Because this manages secrets, prefer a least-privilege identity and a non-production project when an agent acts autonomously.
The universal-auth client secret or `INFISICAL_TOKEN` grants access to your secrets and must itself be treated as a secret.
✓The `codacy_cli_analyze` tool runs Codacy CLI analysis locally on files or directories, and if the CLI is not installed the server will attempt to download and install it, so it can execute and install software on your machine.
The Codacy Account API Token grants API access to the organizations and repositories your account can see, including private ones, so treat it as a secret and scope it to least privilege.
Most tools are read-only analysis (issues, coverage, duplication, security findings), but `codacy_setup_repository` adds or follows a repository in Codacy, which is an account-write action.
Security (SRM) tools surface real vulnerabilities and findings for your code, so handle that output carefully and avoid leaking it.
Prefer a token scoped to the intended organization and a non-sensitive repository when an agent acts autonomously.
✓Write-capable: tools can create and modify real Render infrastructure — create_web_service, create_static_site, create_cron_job, create_postgres, create_key_value, and update_environment_variables provision or change live resources that may incur billing.
update_environment_variables replaces the complete environment variable set for a service; an incomplete array can drop existing variables.
Created services run build and start commands you supply; treat generated commands as code execution on Render's platform.
The server reaches Render's API over the network; the hosted option (https://mcp.render.com/mcp) sends your requests through Render's hosted MCP endpoint.
Review and confirm tool calls before approving them, since an LLM can issue provisioning or env-var changes on your behalf.
✓This server uses a Code Mode scheme — the agent writes TypeScript against the Mux SDK and the server runs it in an isolated sandbox that has no web or filesystem access, then returns what the code prints or returns.
The sandboxed code runs with your Mux access token, so it can create, modify, and delete real Mux resources (assets, live streams, playback IDs, uploads) within that token's permissions.
Access is bounded by the Mux token's permissions, not by tool naming — scope the token to least privilege and prefer a non-production environment when an agent acts autonomously.
Optional Mux signing and private keys enable signed playback URLs and JWTs; treat `MUX_SIGNING_KEY` and `MUX_PRIVATE_KEY` as secrets.
Launching the client with the remote HTTP transport opens a network listener, so secure and authenticate it before exposing it beyond localhost.
Privacy notes
✓The `get-secret` and `list-secrets` tools return secret values to the LLM/MCP client, so plaintext secrets can be exposed to the model and its provider — a significant consideration for a secrets manager.
Avoid pointing the server at production secrets; use a scoped, non-sensitive project for agent workflows where possible.
The identity credentials (client ID/secret or access token) live in your MCP client config env block — keep that config out of version control and restrict access to it.
When self-hosting, `INFISICAL_HOST_URL` targets your own instance, and requests plus credentials are sent there.
✓The server calls the Codacy API with your token; repository metadata, code-quality issues, coverage, duplication, security findings, and pull-request data it returns are passed to the LLM/MCP client.
Some tools return source-derived content — for example `codacy_get_pull_request_git_diff` returns a PR's Git diff and file-analysis tools return issue context — which can include real source code.
Security findings can reveal sensitive vulnerability details about your codebase; review before sharing that output.
The account token is provided via the `CODACY_ACCOUNT_TOKEN` environment variable in your MCP client config — keep that config out of version control and restrict access to it.
✓Authentication uses a RENDER_API_KEY scoped to your Render workspace(s); anyone with the key can manage those resources. Keep it in a server-scoped header or server-scoped env block, not a top-level/global env block shared with other MCP servers.
query_render_postgres runs SQL against your Render Postgres and returns row data to the LLM — query results may include sensitive application data.
Logs and metrics tools (list_logs, list_log_label_values, get_metrics) surface application log contents and performance data to the model.
update_environment_variables and service details can expose configuration values; avoid sending secrets you don't want the model to see.
When using the hosted server, requests transit Render's hosted MCP infrastructure rather than staying entirely local.
✓The server calls the Mux API with your credentials; asset metadata, live-stream details, and Mux Data results it returns are passed to the LLM/MCP client.
Mux Data covers viewer and playback analytics (video views, errors, quality-of-experience metrics), which can include viewer and session information.
Credentials (`MUX_TOKEN_ID`, `MUX_TOKEN_SECRET`, and any signing/webhook secrets) are provided via environment variables in your MCP client config — keep that config out of version control and restrict access to it.
Video assets and analytics can reference real customer-facing content and usage, so avoid exposing a production account's data to the model unnecessarily.
Prerequisites
Node.js and npm (the server runs via `npx -y @infisical/mcp`)
An Infisical account on Infisical Cloud or a self-hosted instance
Credentials — a Machine Identity universal-auth client ID and secret, or an access token (`INFISICAL_TOKEN`)
Optionally `INFISICAL_HOST_URL` for a self-hosted or dedicated instance (defaults to `https://app.infisical.com`)
Node.js and npm, with the `npx` command working (the server runs via `npx -y @codacy/codacy-mcp`)
A Codacy account and an Account API Token from Codacy Account access management
For local analysis, the Codacy CLI v2 (macOS/Linux/Windows via WSL); the server installs it if it is missing
An MCP-compatible client (Claude Desktop, Cursor, VS Code, Windsurf, etc.)
A Render account
A Render API key created from Account Settings (dashboard.render.com/u/settings)
An MCP-compatible client (e.g. Claude Desktop, Cursor)
For the local binary only: the unzipped release executable, or Go to build from source
Node.js and npm (the server runs via `npx -y @mux/mcp@latest`)
A Mux account and an access token (token ID and secret) from the Mux dashboard
Optional Mux signing/private keys or webhook secret if you use signed playback or webhook features
An MCP-compatible client (Claude Desktop, Cursor, VS Code, Windsurf, etc.)
Install
npx -y @infisical/mcp
npx -y @codacy/codacy-mcp
# Recommended: use Render's hosted MCP server (no local install required).
# Optional local binary — download from GitHub Releases, then point your
# MCP client at the unzipped executable:
# https://github.com/render-oss/render-mcp-server/releases